LaserTag: A Tool for Autonomous XAI-Guided Physical Adversarial Perturbations in Industrial Vision Pipelines
Sánchez Collado, Gustavo
1; Li, Wei 1; Hagenmeyer, Veit
1
1 Institut für Automation und angewandte Informatik (IAI), Karlsruher Institut für Technologie (KIT)
1; Li, Wei 1; Hagenmeyer, Veit
11 Institut für Automation und angewandte Informatik (IAI), Karlsruher Institut für Technologie (KIT)
Abstract:
This repository implements a general closed-loop physical attack framework for vision-based monitoring systems. It performs autonomous, XAI-guided laser perturbations and includes a full suite of digital color-filter defenses. Manual attacks using a gamepad are also supported. The system is device-agnostic: adapting to a new device only requires replacing classifier weight files.
For general information, see the main README.md file. See XAI-Auto-Laser-Attack-and-Defense-main/Siemens-Energy-T3000/README.md for a detailed description of a experiment including specific requirements (hardware + sofware) to reproduce results.
For general information, see the main README.md file. See XAI-Auto-Laser-Attack-and-Defense-main/Siemens-Energy-T3000/README.md for a detailed description of a experiment including specific requirements (hardware + sofware) to reproduce results.
| Zugehörige Institution(en) am KIT | Institut für Automation und angewandte Informatik (IAI) |
| Publikationstyp | Forschungsdaten |
| Publikationsdatum | 26.03.2026 |
| Identifikator | KITopen-ID: 1000198998 |
| HGF-Programm | 46.23.02 (POF IV, LK 01) Engineering Security for Energy Systems |
| Lizenz | Creative Commons Namensnennung 4.0 International |
| Schlagwörter | Computer security, Artificial intelligence |
| Art der Forschungsdaten | Software |
| Nachgewiesen in | OpenAlex |